ComfyUI Custom Extensions
Browse 9,420 ComfyUI extensions and 73,215 custom nodes.
Draws Nodes 2.0-only widgets (Compare Images, LoRA stacks, Crop, Video Crop/Trim, Curves, Colors, Bounding Boxes, Resolution preview) on the classic litegraph canvas.
A collection of high-quality nodes for ComfyUI, dedicated to improving the sharpness, clarity, and texture of your images
A simple way to create sprite sheets and image grids.
HSL-based color consistency node for ComfyUI. Supports independent matching of Luminance, Hue, and Saturation with mask protection and bilingual UI.
ComfyUI loader for LTX models with int8 quantization, requiring ComfyKitchen, latest ComfyUI, and Triton. (Description by CC)
A lightweight ComfyUI custom node that applies a direct (1,12) delta patch to diffusion_model.txtfusion.projector.weight, with editable presets, custom value input, and a LoRA-style strength control.
A command palette extension for ComfyUI
Forge fork of Anima-Artist-Mixer: a ComfyUI node pack for multi-artist mixing on the Anima model by hooking into its cross-attention layers.
Enhanced video combination node for ComfyUI with GPU-accelerated preview, sound volume control, video timeline, and frame-to-image export capabilities.
Add a button to the menu to save and load the running queue and the pending queues. This is intended to be used when you want to exit ComfyUI with queues still remaining.
NODES: OverrideLoadedDiffusionDevice. I happen to have two graphics cards, and I want to load models into another graphics card in Comfyui, so I designed this small node.
Various custom nodes for improved usability.
NovelAI image generation for ComfyUI with V5 and Full Medium Effort, img2img, inpainting, multi-character prompts and detailing, combined SEGM/BBOX/SAM detection, local tagger matching, hole/notch filling, image-restored NAI context with selective settings in T2I/img2img/detailer, Vibe Transfer, Precise Reference, reference insets, character assets, prompt weight conversion, PNG/WebP autosave preserving whole-image context and correction history, an integrated metadata loader, and cancellable request timers.
ComfyUI nodes that improve SDXL prompt adherence and any-size/tiled VAE workflows.
Forge fork of Anima-Artist-Mixer: a ComfyUI node pack for multi-artist mixing on the Anima model by hooking into its cross-attention layers.
Complete ComfyUI diffusion pipeline with secure model loading, text conditioning, pipe sampling, and verified downloads.
ComfyUI custom node for KittenTTS - Ultra-lightweight text-to-speech (CUDA / CPU)
Linear EXR plate I/O for Nuke <-> ComfyUI — sequence loading with playback preview, invertible sRGB/Rec.709/Reinhard colorspace transforms, multi-format save, a browse-and-version path builder, and a Nuke bridge.
SDFXBridgeForComfyUI is a custom node designed for seamless integration between ComfyUI and SDFX. This custom node allows users to make ComfyUI compatible with SDFX when running the ComfyUI instance on their local machines.
Virtual camera inside a 360 image. Real focal lengths, sensor sizes, lens projections, interactive drag framing.
A custom node that provides enhanced control over style transfer balance when using FLUX style models in ComfyUI. This node offers better control over the influence of text prompts versus style reference images.
Custom nodes for ComfyUI to generate empty latent space compatible with Hunyuan models for both image and video generation.
A non-destructive overlay that lights up every node by graph distance from the one you click. Diagnostic for big workflows, educational for understanding workflows others built, and surgical when you need to focus on one neighbourhood at a time.
A queue panel for ComfyUI: tell queued runs apart at a glance, edit queued runs in place (the queue freezes meanwhile), drag to reorder, pause, time estimates, and a history with gallery, filters and compare. Survives restarts.
you can using customnet in comfyUI
you can using pic2story in comfyUI
These nodes aid with batching image processing and maintaining input file names in output files and other quality of life nodes.
A custom ComfyUI node to load Hugging Face datasets and make them available for further processing. The node loads a dataset from the Hugging Face Hub or from local/remote files (csv, json, parquet, arrow, text) via the Hugging Face `datasets` library and exposes it as an opaque HUGGINGFACE_DATASET object, ready to be shaped by the pack's transform nodes and turned into ComfyUI data (a Data List / LIST of rows, with image cells as single-image IMAGE values) for generic data-handling node packs such as "Basic data handling".
A two-node MiniMax H3 director desk for storyboards, materials, staged generation, previews and video export.
Dynamic Position Extrapolation for Ultra High Resolution FLUX Image Generation This custom node enables FLUX models in ComfyUI to generate ultra-high resolution images (4K and beyond) using DyPE (Dynamic Position Extrapolation) technology.
Run Python code, Outline, List, Four-quadrant grid, Nine-square grid
Utility nodes for ComfyUI: logic switches, bundle nodes, selectors, bypass nodes, image/latent utilities, and workflow automation nodes.
Alt+P prettifies the workflow, Alt+Shift+P opens the options. Makes ComfyUI workflows readable and good looking: auto-layout by graph flow, link straightening and rerouting, grouping, node and link colors, color palettes, renaming, themes and a lint report, with lots of options.
This node lets you merge two full Krea 2 bf16 models and up to three LoRAs and quantize to int8/int4
A custom node for ComfyUI that provides advanced 2D relighting capabilities.
The Joy Caption Alpha Two node for ComfyUI, based on https://huggingface.co/spaces/fancyfeast/joy-caption-alpha-two
Semantic Timeline, lyrics and generation authoring for MiniMax Music 3 in ComfyUI, with Capture / Freeze Audio workflow and a non-destructive Audio Editor with built-in DSP and optional Windows VST3 hosting.
A ComfyUI custom node for generating high-fidelity, synchronized foley audio for any video, powered by Tencent’s HunyuanVideo-Foley model.
Build VFX-compliant filename prefixes (SHOW_SEQ_SHOT_task_ven_v###) for Save Image and video saver nodes.
A Power-Lora-Loader-style dynamic LoRA stack node with a real on-disk folder browser, drag-to-reorder, optional CLIP, and per-lora split model/clip strengths.
Setting Up a Web Interface Using ComfyUI. NOTE:When installed, you can access it via http://127.0.0.1:8188/comfygen.
This custom node provides the capability to manipulate multiple string inputs.
Professional video save node for ComfyUI - ProRes ladder, All-Intra H.264/H.265, FFV1 lossless. Honest 10-bit pipeline that preserves diffusion float precision.
One-click high-speed inference plugin for MiniMax H3 - Sol-Attn sparse attention + FastH3 4-step distillation + Fused Modulation + Chunk FeedForward + two-pass Self-Lift refine.
ComfyUI nodes for FLUX.2 Klein conditioning: region-aware text enhancement, sectioned prompt encoding, and corrected reference-latent mixing with multi-reference support.
for use jimeng ai in comfyui
Add title, comment and memo functions to nodes, which support custom styles and automatic word wrapping, compatible with Nodes 2.0.
Streaming text-to-video-and-audio (T2VA) nodes for MiniMax H3: a RAVEN model loader and a chunk-major RAVEN streaming sampler, built on ComfyUI's official H3 support.
A simple ComfyUI plugin that Its purpose and function is to replicate some of the editing effects of capcut,jianying and pr.
card-per-image folder viewer with editable prompts and per-image output sockets.
ComfyUI nodes for HiDream-I1 model.
ComfyUI-HunyuanPortrait is now available in ComfyUI, HunyuanPortrait is a diffusion-based condition control method that employs implicit representations for highly controllable and lifelike portrait animation.
ComfyUI nodes for UNO model.
A powerful custom node for ComfyUI that generates rich, dynamic prompts based on modular JSON worlds — with color realm control (RGB / CMYK), LoRA triggers, and optional AI-based prompt enhancement.
Reference-guided image alignment custom node for ComfyUI
A ComfyUI custom node that patches the attention mechanism to use Flash Attention 2 on AMD, similar to how Patch Sage Attention KJ works in KJNodes.
Smart context window model patches for SCAIL-2 long video workflows in ComfyUI.
This is a ComfyUI node package that integrates with VIDU API, supporting features such as text-to-video, image-to-video, character-to-video generation, and video super-resolution.
Control and visualization toolkit (Gatekeeper, Slider) and more in the future.
A comprehensive queue management system for ComfyUI workflows
Folder-based batch queue helpers for ComfyUI
a custom node for [a/EzAudio](https://github.com/haidog-yaqub/EzAudio)
TeleStyle custom nodes for ComfyUI video style transfer and official Qwen image style transfer.
Custom nodes to run microsoft/Phi models.
Custom ComfyUI nodes for StoryMem - Multi-shot long video storytelling with memory-conditioned video diffusion models.
ComfyUI custom nodes for Cosmos reference latent conditioning.
A comprehensive set of naming tools for ComfyUI to build, sanitize, and manage file names and paths.
Export AI-generated images and video with invisible watermarks, C2PA and receipts using your own Ariadne Mark SDK kit.
All-in-one face styling node for ComfyUI: curated style presets with auto-fill prompts, FaceDetailer parameters, and a dynamic searchable LoRA stack. Outputs CONDITIONING + modified MODEL ready for FaceDetailer / KSampler.
An interactive 3D motion reference custom node for ComfyUI.
Custom FP8 compute kernels for Apple Silicon (MPS)
ComfyUI Nodes for HPSv2, Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis
Custom ComfyUI node for using Qwen-Image-Layered as a conversion tool to transform layer numbers into latent space length parameters. (Description by CC)
Add text to image in ComfyUI
DiffRhythm2 歌曲生成。
OuteTTS - Unified Text-To-Speech. A node for ComfyUI
Automatic image tagging using WD14 models with batch processing and GPU acceleration for ComfyUI
Quickly create empty latents in common resolutions and aspect ratios for SD 1.5, SDXL, Flux, Chroma, and HiDream. Choose from curated presets or generate by axis and aspect ratio. Appears in the 'latent' node group.
Custom node for ComfyUI that allows you to analyze songs using NVIDIA's Music Flamingo.
FlashAttention-2 Triton kernel for AMD RDNA3 (gfx1100 / Radeon RX 7900 XT/XTX/GRE)
This is a ComfyUI implementation of the timestep shift technique used in [a/NitroFusion: High-Fidelity Single-Step Diffusion through Dynamic Adversarial Training.](https://arxiv.org/abs/2412.02030) For more details, visit the official [a/NitroFusion GitHub repository](https://github.com/ChenDarYen/NitroFusion).
Modern Deforum-style animation toolkit for ComfyUI: math-driven keyframe schedules, audio reactivity, depth-aware camera warping and a Wan 2.2 video bridge.
Some mathematical calculation nodes,freedom And omnipotent, string calculation nodes, can customize the number of parameters and calculation formulas(expression). The calculation content can also be displayed in places such as the label title of Comfy Node,String to Image Title Label
A ComfyUI scheduler that finds the shift value required to align high/low sampling steps with a target sigma boundary.
Real-time monitoring and statistics for ComfyUI
A drop-in ComfyUI LoRA loader with optional spectral cleanup (energy trimming + hot-layer taming) to reduce artifacts from stacked LoRAs and turbo/distilled models.
This Comfyui node creates an anaglyph image from a color and depth map input. It achieves high speeds suitable for video to anaglyph conversion by using CUDA GPU acceleration.
ComfyUI custom node for fast reference-based LoRA training.
ComfyUI custom nodes for posting images, fetching model/image metadata, and interacting with Civitai daily challenges via the Civitai MCP server.
A collection of custom nodes for ComfyUI.
A collection of custom nodes for ComfyUI.
A professional ComfyUI custom node for browsing and loading LoRA files with folder tree navigation, multi-slot support, and instant preview.
A collection of unusual but useful image processing nodes for ComfyUI.
Distributed image generation for ComfyUI with Thinkbox Deadline integration (master/worker via render farm)
A custom node implementation for ComfyUI that integrates with venice.ai's Flux and SDXL image generation models. This project is adapted from [a/ComfyUI-FLUX-TOGETHER-API](https://github.com/BZcreativ/ComfyUI-FLUX-TOGETHER-API) to work with the venice.ai API.
A Simple App U See. A simple alternative User Interface for Image and Video Generation using ComfyUI as backend.
Enhanced Text Encoder modules, acd Custom nodes for ComfyUI, device-select CLIP loaders, providing HDR effects, image saving with prompt metadata.
Standalone version of ComfyUI's PreviewImage and SaveImage nodes, extracted as an independent custom node for easy reuse and customization.
A collection of ComfyUI custom nodes for interacting with various cloud services. These nodes are designed to work with any ComfyUI instance, including cloud-hosted environments (such as MimicPC) where users may have limited system access.